Simulating the time projection chamber responses at the MPD detector using generative adversarial networks

  title={Simulating the time projection chamber responses at the MPD detector using generative adversarial networks},
  author={Artem Maevskiy and Fedor Ratnikov and A. Zinchenko and V. Riabov},
  journal={The European Physical Journal C},
High energy physics experiments rely heavily on the detailed detector simulation models in many tasks. Running these detailed models typically requires a notable amount of the computing time available to the experiments. In this work, we demonstrate a new approach to speed up the simulation of the Time Projection Chamber tracker of the MPD experiment at the NICA accelerator complex. Our method is based on a Generative Adversarial Network – a deep learning technique allowing for implicit… 

Generative surrogates for fast simulation: TPC case

Generative Adversarial Networks for the fast simulation of the Time Projection Chamber responses at the MPD detector

This work demonstrates the applicability of Generative Adversarial Networks (GAN) as a basis for fast-simulation models for the case of the Time Projection Chamber (TPC) at the MPD detector at the NICA accelerator complex.

Towards Reliable Neural Generative Modeling of Detectors

The application of generative adversarial networks (GANs) to the simulation of the LHCb experiment events is discussed and main pitfalls in the application of GANs are emphasized and study the systematic effects in detail.

Score-based Generative Models for Calorimeter Shower Simulation

CaloScore is the first application of a score-based generative model in collider physics and is able to produce high-fidelity calorimeter images for all datasets, providing an alternative paradigm forcalorimeter shower simulation.

Towards a deep learning model for hadronization

This work replaces a compont of the hadronization model within the Herwig event generator (cluster model) with a Generative Adversarial Network (GAN), and shows that a GAN is capable of reproducing the kinematic properties of cluster decays.

New directions for surrogate models and differentiable programming for High Energy Physics detector simulation

In this document, new and ongoing efforts for surrogate models and differential programming applied to detector simulation are discussed in the context of the 2021 Particle Physics Community Planning Exercise (`Snowmass').

CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows

It is demonstrated that normalizing flows can reproduce many-channel calorimeter showers with extremely high fidelity, providing a fresh alternative to computationally expensive GEANT4 simulations, as well as other state-of-the-art fast simulation frameworks based on GANs and VAEs.

Latent Space Refinement for Deep Generative Models

This work demonstrates how latent space refinement via iterated generative modeling can circumvent topological obstructions and improve precision and shows how this methodology also applies to cases were the target model is non-differentiable and has many internal latent dimensions which must be marginalized over before refinement.

A Living Review of Machine Learning for Particle Physics

This living review is a nearly comprehensive list of citations for those developing and applying deep learning approaches to experimental, phenomenological, or theoretical analyses, and will be updated as often as possible to incorporate the latest developments.

Generative Models for Fast Cluster Simulations in the TPC for the ALICE Experiment

This work introduces research aiming at fast generation of the possible responses of detector clusters to particle collisions, and presents a method to simulate data samples possible to record in the detector based on the initial information about particles.

Fast simulation methods in ATLAS: from classical to generative models

The new tools for fast production of simulated events and an exploratory analysis of the deep learning methods are described, which are expected to improve modeling of correlations within showers.

DCTRGAN: improving the precision of generative models with reweighting

A post-hoc correction to deep generative models to further improve their fidelity, based on the Deep neural networks using the Classification for Tuning and Reweighting (DCTR) protocol is introduced.

GANplifying event samples

A critical question concerning generative networks applied to event generation in particle physics is if the generated events add statistical precision beyond the training sample. We show for a

MPD TPC status

In the frame of the JINR scientific program on study of hot and dense baryonic matter a new accelerator complex Ion Collider fAcility (NICA) based on the Nuclotron-M is under realization. Two

Performance of the MPD Detector in the Study of the Strangeness to Entropy Ratio in Heavy-Ion Collisions at the NICA Accelerator Complex

Strangeness production in heavy-ion collisions is one of the main goals of the scientific program at the NICA accelerator complex. The MPD detector is designed to study the properties of strongly

Towards a computer vision particle flow

In High Energy Physics experiments Particle Flow (PFlow) algorithms are designed to provide an optimal reconstruction of the nature and kinematic properties of the particles produced within the

ML-assisted versatile approach to Calorimeter R&D

A versatile approach to this task that is based on machine learning and can substitute the most computationally intensive steps of the process while retaining the GEANT4 accuracy to details is proposed.

Perspectives of Multistrange Hyperon Study at NICA/MPD from Realistic Monte Carlo Simulation

One of the main tasks of the NICA/MPD physics program is a study of strangeness production in nuclear collisions. In this paper the MPD detector performance for measurements of multistrange hyperons

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

The motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and they are compared to compare their commonalities and differences.